Files
kubesolo-os/update/pkg/config/config.go
Adolfo Delorenzo 9fb894c5af
Some checks failed
ARM64 Build / Build generic ARM64 disk image (push) Failing after 4s
CI / Go Tests (push) Successful in 1m29s
CI / Shellcheck (push) Successful in 48s
CI / Build Go Binaries (amd64, linux, linux-amd64) (push) Successful in 1m12s
CI / Build Go Binaries (arm64, linux, linux-arm64) (push) Has been cancelled
feat(update): pre-flight gates + deeper healthcheck + auto-rollback
Phase 8 of v0.3. Tightens the update lifecycle on both ends.

Pre-flight (apply.go, before any download):
- Free-space check on the passive partition: image size + 10% headroom must
  be available. Uses statfs(2) via the new pkg/partition.FreeBytes /
  HasFreeSpaceFor helpers (tests cover happy path, tiny request, huge
  request, missing path). Catches corrupted-FS and shrunk-partition cases
  before we destroy the existing slot data.
- Node-block-label check: refuses if the local K8s node carries the
  updates.kubesolo.io/block=true label. New pkg/health.CheckNodeBlocked
  shells out to kubectl per the project's zero-deps stance. Silently bypassed
  when no kubeconfig is reachable (air-gap case). Skipped by --force.

Healthcheck (extended via new pkg/health/extended.go + preflight.go):
- CheckKubeSystemReady waits until every kube-system pod has held the Running
  phase for >= N seconds (default 30). Catches "started ok, will crash-loop"
  bugs that a single-shot phase check misses.
- CheckProbeURL fetches an operator-supplied URL; 200 = pass. Wired through
  update.conf as healthcheck_url= and cloud-init updates.healthcheck_url.
- CheckDiskWritable writes/fsyncs/reads a 1-KiB probe under /var/lib/kubesolo.
  Always runs in healthcheck so a wedged data partition fails fast.
- pkg/health.Status grows KubeSystemReady, ProbeURL, DiskWritable booleans.
  Optional checks default to true in RunAll() so they don't block when
  unconfigured. health_test.go updated to the new 6-field shape.

Auto-rollback (healthcheck.go):
- state.UpdateState gains HealthCheckFailures (consecutive post-Activated
  failures). Reset on a clean pass.
- --auto-rollback-after N (also auto_rollback_after= in update.conf) triggers
  env.ForceRollback() when the failure count reaches the threshold. State
  transitions to RolledBack with a descriptive LastError. The command still
  exits with the healthcheck error; the operator/init is expected to reboot.
- Only fires while Phase == Activated. Doesn't second-guess a long-stable
  system that happens to fail one healthcheck.

config / opts / cloud-init plumbing:
- update.conf gains healthcheck_url= and auto_rollback_after= keys.
- New CLI flags: --healthcheck-url, --auto-rollback-after, --kube-system-settle.
- cloud-init full-config.yaml documents the new updates: subfields.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 19:08:30 -06:00

106 lines
2.8 KiB
Go

// Package config parses /etc/kubesolo/update.conf — the persistent
// configuration for the update agent. Each line is "key = value"; blank
// lines and "#"-prefixed comments are ignored. Unknown keys are tolerated
// (forward compatibility).
//
// Example:
//
// # Where to look for updates
// server = https://updates.kubesolo.example.com
// channel = stable
//
// # Only apply between 03:00 and 05:00 local time
// maintenance_window = 03:00-05:00
//
// pubkey = /etc/kubesolo/update-pubkey.hex
//
// The file is populated on first boot by cloud-init (see the cloud-init
// updates: block) and can be hand-edited afterwards.
package config
import (
"bufio"
"fmt"
"os"
"strings"
)
// DefaultPath is where update.conf lives on a live system.
const DefaultPath = "/etc/kubesolo/update.conf"
// Config holds the parsed update.conf values. Empty fields mean "not set" —
// the caller's defaults apply.
type Config struct {
Server string
Channel string
MaintenanceWindow string
PubKey string
// HealthcheckURL is an optional URL the healthcheck command will GET;
// 200 = pass, anything else = fail.
HealthcheckURL string
// AutoRollbackAfter is the number of consecutive post-boot healthcheck
// failures after which the agent will call Rollback automatically.
// 0 = disabled (default).
AutoRollbackAfter int
}
// Load reads and parses update.conf. A missing file returns an empty Config
// (not an error) — fresh systems before cloud-init has run.
func Load(path string) (*Config, error) {
f, err := os.Open(path)
if err != nil {
if os.IsNotExist(err) {
return &Config{}, nil
}
return nil, fmt.Errorf("open %s: %w", path, err)
}
defer f.Close()
c := &Config{}
scanner := bufio.NewScanner(f)
lineNo := 0
for scanner.Scan() {
lineNo++
line := strings.TrimSpace(scanner.Text())
if line == "" || strings.HasPrefix(line, "#") {
continue
}
eq := strings.IndexByte(line, '=')
if eq < 0 {
return nil, fmt.Errorf("%s:%d: missing '=' in line: %q", path, lineNo, line)
}
key := strings.TrimSpace(line[:eq])
value := strings.TrimSpace(line[eq+1:])
switch key {
case "server":
c.Server = value
case "channel":
c.Channel = value
case "maintenance_window":
c.MaintenanceWindow = value
case "pubkey":
c.PubKey = value
case "healthcheck_url":
c.HealthcheckURL = value
case "auto_rollback_after":
// Parse a small integer. Non-numeric values are silently
// ignored (forward compat); zero disables the feature.
n := 0
for _, ch := range value {
if ch >= '0' && ch <= '9' {
n = n*10 + int(ch-'0')
} else {
n = 0
break
}
}
c.AutoRollbackAfter = n
}
// Unknown keys are silently ignored for forward compatibility.
}
if err := scanner.Err(); err != nil {
return nil, fmt.Errorf("read %s: %w", path, err)
}
return c, nil
}